arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2209.09043cs.CV
收藏

结构感知的三维VR草图到三维形状检索

Structure-Aware 3D VR Sketch to 3D Shape Retrieval

University of Surrey(萨里大学);iFlyTek-Surrey Joint Research Centre on Artificial Intelligence(讯飞-萨里人工智能联合研究中心);Surrey Institute for People Centred AI(萨里以人为本人工智能研究所)

Ling Luo, Yulia Gryaditskaya, Tao Xiang, Yi-Zhe Song

摘要:

研究了基于草图的细粒度三维形状检索的实际任务。这项任务是特别感兴趣的2D草图被证明是有效的查询2D图像。然而,由于域间隙,它仍然很难实现强大的性能,在三维形状检索从二维草图。最近的工作证明了3D VR草图在这项任务上的优势。在我们的工作中,我们专注于3D VR草图中固有的不准确性所带来的挑战。我们观察到,检索结果与一个固定的保证金值,通常用于检索任务的三重损失,包含许多不相关的形状,往往只有一个或几个具有类似的结构的查询。为了缓解这个问题,我们第一次绘制自适应边缘值和形状相似性之间的连接。特别是,我们建议使用一个自适应的利润率值驱动的“拟合间隙”,这是结构保持变形下的两个形状的相似性的三重损失。我们还进行了用户研究,证实了这个拟合间隙确实是一个合适的标准来评估形状的结构相似性。此外,我们介绍了一个数据集的202 VR草图202 3D形状从内存中绘制,而不是从观察。代码和数据可在https://github.com/Rowl1ng/Structure-Aware-VR-Sketch-Shape-Retrieval上获得。

英文摘要:

We study the practical task of fine-grained 3D-VR-sketch-based 3D shape retrieval. This task is of particular interest as 2D sketches were shown to be effective queries for 2D images. However, due to the domain gap, it remains hard to achieve strong performance in 3D shape retrieval from 2D sketches. Recent work demonstrated the advantage of 3D VR sketching on this task. In our work, we focus on the challenge caused by inherent inaccuracies in 3D VR sketches. We observe that retrieval results obtained with a triplet loss with a fixed margin value, commonly used for retrieval tasks, contain many irrelevant shapes and often just one or few with a similar structure to the query. To mitigate this problem, we for the first time draw a connection between adaptive margin values and shape similarities. In particular, we propose to use a triplet loss with an adaptive margin value driven by a "fitting gap", which is the similarity of two shapes under structure-preserving deformations. We also conduct a user study which confirms that this fitting gap is indeed a suitable criterion to evaluate the structural similarity of shapes. Furthermore, we introduce a dataset of 202 VR sketches for 202 3D shapes drawn from memory rather than from observation. The code and data are available at https://github.com/Rowl1ng/Structure-Aware-VR-Sketch-Shape-Retrieval.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑